相关论文: Magnitude and Phase-based Feature Fusion Using Co-…

Transformer-based speech recognition models have achieved great success due to the self-attention (SA) mechanism that utilizes every frame in the feature extraction process. Especially, SA heads in lower layers capture various phonetic…

Due to the high computational complexity to model more frequency bands, it is still intractable to conduct real-time full-band speech enhancement based on deep neural networks. Recent studies typically utilize the compressed perceptually…

Facial Expression Recognition (FER) is a critical task within computer vision with diverse applications across various domains. Addressing the challenge of limited FER datasets, which hampers the generalization capability of expression…

Target speech separation refers to extracting a target speaker's voice from an overlapped audio of simultaneous talkers. Previously the use of visual modality for target speech separation has demonstrated great potentials. This work…

Speech emotion recognition (SER) is crucial for enhancing affective computing and enriching the domain of human-computer interaction. However, the main challenge in SER lies in selecting relevant feature representations from speech signals…

The audio-video based multimodal emotion recognition has attracted a lot of attention due to its robust performance. Most of the existing methods focus on proposing different cross-modal fusion strategies. However, these strategies…

Transformer based end-to-end modelling approaches with multiple stream inputs have been achieved great success in various automatic speech recognition (ASR) tasks. An important issue associated with such approaches is that the intermediate…

Humans perceive the world by concurrently processing and fusing high-dimensional inputs from multiple modalities such as vision and audio. Machine perception models, in stark contrast, are typically modality-specific and optimised for…

The joint training framework for speech enhancement and recognition methods have obtained quite good performances for robust end-to-end automatic speech recognition (ASR). However, these methods only utilize the enhanced feature as the…

Most of the prior studies in the spatial \ac{DoA} domain focus on a single modality. However, humans use auditory and visual senses to detect the presence of sound sources. With this motivation, we propose to use neural networks with audio…

The use of multi-modal data for deep machine learning has shown promise when compared to uni-modal approaches with fusion of multi-modal features resulting in improved performance in several applications. However, most state-of-the-art…

Initially developed for natural language processing (NLP), Transformer model is now widely used for speech processing tasks such as speaker recognition, due to its powerful sequence modeling capabilities. However, conventional…

In this paper, a hierarchical attention network to generate utterance-level embeddings (H-vectors) for speaker identification is proposed. Since different parts of an utterance may have different contributions to speaker identities, the use…

We propose a multi-stage framework for universal speech enhancement, designed for the Interspeech 2025 URGENT Challenge. Our system first employs a Sparse Compression Network to robustly separate sources and extract an initial clean speech…

Sentiment analysis, mostly based on text, has been rapidly developing in the last decade and has attracted widespread attention in both academia and industry. However, the information in the real world usually comes from multiple…

Target speaker extraction focuses on extracting a target speech signal from an environment with multiple speakers by leveraging an enrollment. Existing methods predominantly rely on speaker embeddings obtained from the enrollment,…

Recently, hyperspherical embeddings have established themselves as a dominant technique for face and voice recognition. Specifically, Euclidean space vector embeddings are learned to encode person-specific information in their direction…

This paper proposes attentive statistics pooling for deep speaker embedding in text-independent speaker verification. In conventional speaker embedding, frame-level features are averaged over all the frames of a single utterance to form an…

Speech Emotion Recognition (SER) plays a key role in advancing human-computer interaction. Attention mechanisms have become the dominant approach for modeling emotional speech due to their ability to capture long-range dependencies and…

Identifying multiple speakers without knowing where a speaker's voice is in a recording is a challenging task. In this paper, a hierarchical attention network is proposed to solve a weakly labelled speaker identification problem. The use of…